In Defence of RANSAC for Outlier Rejection in Deformable Registration

  • Quoc-Huy Tran
  • Tat-Jun Chin
  • Gustavo Carneiro
  • Michael S. Brown
  • David Suter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7575)


This paper concerns the robust estimation of non-rigid deformations from feature correspondences. We advance the surprising view that for many realistic physical deformations, the error of the mismatches (outliers) usually dwarfs the effects of the curvature of the manifold on which the correct matches (inliers) lie, to the extent that one can tightly enclose the manifold within the error bounds of a low-dimensional hyperplane for accurate outlier rejection. This justifies a simple RANSAC-driven deformable registration technique that is at least as accurate as other methods based on the optimisation of fully deformable models. We support our ideas with comprehensive experiments on synthetic and real data typical of the deformations examined in the literature.


Thin Plate Spline Deformable Surface Deformable Registration Outlier Rejection Local Smoothness 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Pilet, J., Lepetit, V., Fua, P.: Real-time non-rigid surface detection. In: CVPR (2005)Google Scholar
  2. 2.
    Pilet, J., Lepetit, V., Fua, P.: Fast non-rigid surface detection, registration and realistic augmentation. IJCV 76, 109–122 (2008)CrossRefGoogle Scholar
  3. 3.
    Zhu, J., Lyu, M.R.: Progressive finite newton approach to real-time nonrigid surface detection. In: CVPR (2007)Google Scholar
  4. 4.
    Zhu, J., Hoi, C.H., Lyu, M.R.: Nonrigid shape recovery by gaussian process registration. In: CVPR (2009)Google Scholar
  5. 5.
    Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE TPAMI 11, 567–585 (1989)zbMATHCrossRefGoogle Scholar
  6. 6.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24 (1981)Google Scholar
  7. 7.
    Carneiro, G., Jepson, A.D.: Flexible spatial configuration of local image features. IEEE TPAMI 29, 2089–2104 (2007)CrossRefGoogle Scholar
  8. 8.
    Bartoli, A.: Maximizing the predictivity of smooth deformable image warps through cross-validation. J. Math. Imaging Vis. 31, 233–244 (2008)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Pizarro, D., Bartoli, A.: Feature-based deformable surface detection with self-occlusion reasoning. IJCV (to appear)Google Scholar
  10. 10.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  11. 11.
    Li, X., Hu, Z.: Rejecting mismatches by correspondence function. IJCV 89, 1–17 (2010)CrossRefGoogle Scholar
  12. 12.
    Chum, O., Matas, J.: Matching with prosac - progressive sample consensus. In: CVPR (2005)Google Scholar
  13. 13.
    Li, X., Li, X., Li, H., Cao, M.: Rejecting outliers based on correspondence manifold. Acta Automatica Sinica 35, 17–22 (2009)CrossRefGoogle Scholar
  14. 14.
    Bartoli, A., Zisserman, A.: Direct estimation of non-rigid registrations. In: BMVC (2004)Google Scholar
  15. 15.
    Gay-Bellile, V., Bartoli, A., Sayd, P.: Direct estimation of nonrigid registrations with image-based self-occlusion reasoning. IEEE TPAMI 32, 87–104 (2010)CrossRefGoogle Scholar
  16. 16.
    Varol, A., Salzmann, M., Tola, E., Fua, P.: Template-free monocular reconstruction of deformable surfaces. In: ICCV (2009)Google Scholar
  17. 17.
    Taylor, J., Jepson, A., Kutulakos, K.: Non-rigid structure from locally rigid motion. In: CVPR (2010)Google Scholar
  18. 18.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE TPAMI 24, 509–521 (2002)CrossRefGoogle Scholar
  19. 19.
    Chui, H., Rangarajan, A.: A new point matching algorithm for non-rigid registration. CVIU 89, 114–141 (2003)zbMATHGoogle Scholar
  20. 20.
    Choi, S., Kim, T., Yu, W.: Performance evaluation of RANSAC family. In: BMVC (2009)Google Scholar
  21. 21.
    Chen, H., Meer, P.: Robust regression with projection based m-estimators. In: ICCV (2003)Google Scholar
  22. 22.
    Rozenfeld, S., Shimshoni, I.: The modified pbm-estimator method and a runtime analysis technique for the ransac family. In: CVPR (2005)Google Scholar
  23. 23.
    Donato, G., Belongie, S.: Approximate Thin Plate Spline Mappings. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part III. LNCS, vol. 2352, pp. 21–31. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  24. 24.
    Salzmann, M., Fua, P.: Reconstructing sharply folding surfaces: a convex formulation. In: CVPR (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Quoc-Huy Tran
    • 1
  • Tat-Jun Chin
    • 1
  • Gustavo Carneiro
    • 1
  • Michael S. Brown
    • 2
  • David Suter
    • 1
  1. 1.School of Computer ScienceThe University of AdelaideAustralia
  2. 2.School of ComputingNational University of SingaporeSingapore

Personalised recommendations